In [9]:
plt.style.use('seaborn-whitegrid')
plt.figure(figsize=(20, 10))
sns.heatmap(data.corr())
plt.show()
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import plotly.express as px
data=pd.read_csv("C://Users//gajja//Downloads//Unemployment in India.csv")
data1=pd.read_csv("C://Users//gajja//Downloads//Unemployment_Rate_upto_11_2020.csv")
print(data.head())
Region Date Frequency Estimated Unemployment Rate (%) \
0 Andhra Pradesh 31-05-2019 Monthly 3.65
1 Andhra Pradesh 30-06-2019 Monthly 3.05
2 Andhra Pradesh 31-07-2019 Monthly 3.75
3 Andhra Pradesh 31-08-2019 Monthly 3.32
4 Andhra Pradesh 30-09-2019 Monthly 5.17
Estimated Employed Estimated Labour Participation Rate (%) Area
0 11999139.0 43.24 Rural
1 11755881.0 42.05 Rural
2 12086707.0 43.50 Rural
3 12285693.0 43.97 Rural
4 12256762.0 44.68 Rural
print(data.info())
<class 'pandas.core.frame.DataFrame'> RangeIndex: 768 entries, 0 to 767 Data columns (total 7 columns): # Column Non-Null Count Dtype --- ------ -------------- ----- 0 Region 740 non-null object 1 Date 740 non-null object 2 Frequency 740 non-null object 3 Estimated Unemployment Rate (%) 740 non-null float64 4 Estimated Employed 740 non-null float64 5 Estimated Labour Participation Rate (%) 740 non-null float64 6 Area 740 non-null object dtypes: float64(3), object(4) memory usage: 42.1+ KB None
print(data1.info())
<class 'pandas.core.frame.DataFrame'> RangeIndex: 267 entries, 0 to 266 Data columns (total 9 columns): # Column Non-Null Count Dtype --- ------ -------------- ----- 0 Region 267 non-null object 1 Date 267 non-null object 2 Frequency 267 non-null object 3 Estimated Unemployment Rate (%) 267 non-null float64 4 Estimated Employed 267 non-null int64 5 Estimated Labour Participation Rate (%) 267 non-null float64 6 Region.1 267 non-null object 7 longitude 267 non-null float64 8 latitude 267 non-null float64 dtypes: float64(4), int64(1), object(4) memory usage: 18.9+ KB None
print(data1.head())
Region Date Frequency Estimated Unemployment Rate (%) \
0 Andhra Pradesh 31-01-2020 M 5.48
1 Andhra Pradesh 29-02-2020 M 5.83
2 Andhra Pradesh 31-03-2020 M 5.79
3 Andhra Pradesh 30-04-2020 M 20.51
4 Andhra Pradesh 31-05-2020 M 17.43
Estimated Employed Estimated Labour Participation Rate (%) Region.1 \
0 16635535 41.02 South
1 16545652 40.90 South
2 15881197 39.18 South
3 11336911 33.10 South
4 12988845 36.46 South
longitude latitude
0 15.9129 79.74
1 15.9129 79.74
2 15.9129 79.74
3 15.9129 79.74
4 15.9129 79.74
print(data.describe())
Estimated Unemployment Rate (%) Estimated Employed \
count 740.000000 7.400000e+02
mean 11.787946 7.204460e+06
std 10.721298 8.087988e+06
min 0.000000 4.942000e+04
25% 4.657500 1.190404e+06
50% 8.350000 4.744178e+06
75% 15.887500 1.127549e+07
max 76.740000 4.577751e+07
Estimated Labour Participation Rate (%)
count 740.000000
mean 42.630122
std 8.111094
min 13.330000
25% 38.062500
50% 41.160000
75% 45.505000
max 72.570000
print(data1.describe())
Estimated Unemployment Rate (%) Estimated Employed \
count 267.000000 2.670000e+02
mean 12.236929 1.396211e+07
std 10.803283 1.336632e+07
min 0.500000 1.175420e+05
25% 4.845000 2.838930e+06
50% 9.650000 9.732417e+06
75% 16.755000 2.187869e+07
max 75.850000 5.943376e+07
Estimated Labour Participation Rate (%) longitude latitude
count 267.000000 267.000000 267.000000
mean 41.681573 22.826048 80.532425
std 7.845419 6.270731 5.831738
min 16.770000 10.850500 71.192400
25% 37.265000 18.112400 76.085600
50% 40.390000 23.610200 79.019300
75% 44.055000 27.278400 85.279900
max 69.690000 33.778200 92.937600
print(data.isnull().sum())
Region 28 Date 28 Frequency 28 Estimated Unemployment Rate (%) 28 Estimated Employed 28 Estimated Labour Participation Rate (%) 28 Area 28 dtype: int64
print(data1.isnull().sum())
Region 0 Date 0 Frequency 0 Estimated Unemployment Rate (%) 0 Estimated Employed 0 Estimated Labour Participation Rate (%) 0 Region.1 0 longitude 0 latitude 0 dtype: int64
print(data.fillna(0))
Region Date Frequency Estimated Unemployment Rate (%) \
0 Andhra Pradesh 31-05-2019 Monthly 3.65
1 Andhra Pradesh 30-06-2019 Monthly 3.05
2 Andhra Pradesh 31-07-2019 Monthly 3.75
3 Andhra Pradesh 31-08-2019 Monthly 3.32
4 Andhra Pradesh 30-09-2019 Monthly 5.17
.. ... ... ... ...
763 0 0 0 0.00
764 0 0 0 0.00
765 0 0 0 0.00
766 0 0 0 0.00
767 0 0 0 0.00
Estimated Employed Estimated Labour Participation Rate (%) Area
0 11999139.0 43.24 Rural
1 11755881.0 42.05 Rural
2 12086707.0 43.50 Rural
3 12285693.0 43.97 Rural
4 12256762.0 44.68 Rural
.. ... ... ...
763 0.0 0.00 0
764 0.0 0.00 0
765 0.0 0.00 0
766 0.0 0.00 0
767 0.0 0.00 0
[768 rows x 7 columns]
data.columns=["States","Date","Freq","Estimated Unemployment Rate","Estimated Employed",
"Estimated Labour Participation Rate","Region"]
data1.columns=["States","Date","Freq","Estimated Unemployment Rate","Estimated Employed",
"Estimated Labour Participation Rate","Region","Longi","Lati"]
plt.style.use('seaborn-whitegrid')
plt.figure(figsize=(20, 10))
sns.heatmap(data.corr())
plt.show()
plt.figure(figsize=(20, 10))
plt.title("Unemployement Rate Fluctuations Upto 2020")
sns.histplot(data1,x="Estimated Unemployment Rate",hue="Region");
plt.figure(figsize=(20, 10))
plt.title("Unemployement Rate Fluctuations After 2020")
sns.histplot(data,x="Estimated Unemployment Rate",hue="Region");
plt.figure(figsize=(20, 10))
plt.title("After 2020")
sns.histplot(data,x="Estimated Unemployment Rate",hue="States");
plt.figure(figsize=(20, 10))
plt.title("Upto 2020")
sns.histplot(data1,x="Estimated Unemployment Rate",hue="States");
emp = data1[["Estimated Unemployment Rate","States","Region"]]
fig = px.sunburst(emp,path=["Region","States"],values="Estimated Unemployment Rate",width=500,height=500)
fig.show()